no code implementations • 21 Jan 2025 • Siyuan Chen, Hanshen Yu, Jamal Yagoobi, Chenhui Shao
Existing approaches to enforcing design constraints in Reinforcement Learning (RL) applications often rely on training-time penalties in the reward function or training/inference-time invalid action masking, but these methods either cannot be modified after training, or are limited in the types of constraints that can be implemented.
no code implementations • 31 Dec 2024 • Yiwen Wang, Siyuan Chen, Ran Yi
We introduce SG-Splatting with Spherical Gaussians based color representation, a novel approach to enhance rendering speed and quality in novel view synthesis.
no code implementations • 4 Nov 2024 • Siyuan Chen, Qingyi Si, Chenxu Yang, Yunzhi Liang, Zheng Lin, Huan Liu, Weiping Wang
The advent of large language models (LLMs) has significantly propelled the advancement of Role-Playing Agents (RPAs).
no code implementations • 28 Oct 2024 • Siyuan Chen, Jiahai Wang
Dynamical complex systems composed of interactive heterogeneous agents are prevalent in the world, including urban traffic systems and social networks.
no code implementations • 29 Sep 2024 • Siyuan Chen, Cong Ming, Zhiling Zhang, Yanyi Chen, Kenny Q. Zhu, Mengyue Wu
In the realm of mental health support chatbots, it is vital to show empathy and encourage self-exploration to provide tailored solutions.
no code implementations • 23 Sep 2024 • Chenxu Yang, Ruipeng Jia, Naibin Gu, Zheng Lin, Siyuan Chen, Chao Pang, Weichong Yin, Yu Sun, Hua Wu, Weiping Wang
Hence, we introduce orthogonal finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method, which merely conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant, thereby preserving the knowledge encoded in the angle between neurons.
no code implementations • 20 Sep 2024 • Kunyao Lan, Bingrui Jin, Zichen Zhu, Siyuan Chen, Shu Zhang, Kenny Q. Zhu, Mengyue Wu
Mental health issues, particularly depressive disorders, present significant challenges in contemporary society, necessitating the development of effective automated diagnostic methods.
no code implementations • 2 Aug 2024 • Yuanzhi Su, Siyuan Chen, Yuan-Gen Wang
For the performance breakthrough of CIL, it is essential yet challenging to effectively refine past knowledge from the base model and balance it with new learning.
class-incremental learning
Class-Incremental Semantic Segmentation
+2
no code implementations • 14 Jun 2024 • Siyuan Chen, Zhuofeng Wang, Zelong Guan, Yudong Liu, Phillip B. Gibbons
However, this approach is hampered by the limited bandwidth of commodity hardware, which constrains communication between the CPU and GPU, and by slower matrix multiplications on the CPU.
2 code implementations • 31 May 2024 • Mingyang Jiang, Yueyuan Li, Songan Zhang, Siyuan Chen, Chunxiang Wang, Ming Yang
This novel solution integrates a reinforcement learning agent with Reeds-Shepp curves, enabling effective planning across diverse scenarios.
no code implementations • 18 Jan 2024 • Siyuan Chen, Xin Du, Jiahai Wang
Agents' and the system's representations are learned to preserve the spatio-temporal consistency by minimizing the spatial and temporal dissimilarities in a self-supervised manner in the latent space.
no code implementations • 15 Dec 2023 • Yige Chen, Teng Hu, Yizhe Tang, Siyuan Chen, Ang Chen, Ran Yi
With the help of Score Distillation Sampling (SDS) and the rapid development of neural 3D representations, some methods have been proposed to perform 3D editing such as adding additional geometries, or overwriting textures.
1 code implementation • 15 Nov 2023 • Haoan Jin, Siyuan Chen, Dilawaier Dilixiati, Yewei Jiang, Mengyue Wu, Kenny Q. Zhu
This comprehensive framework is designed to thoroughly assess the unique challenges and intricacies of mental health-related tasks, making PsyEval a highly specialized and valuable tool for evaluating LLM performance in this domain.
1 code implementation • 6 Sep 2023 • Juexiao Zhou, Bin Zhang, Xiuying Chen, Haoyang Li, Xiaopeng Xu, Siyuan Chen, Xin Gao
With the fast-growing and evolving omics data, the demand for streamlined and adaptable tools to handle the analysis continues to grow.
1 code implementation • 5 Sep 2023 • Eric Youn, Sai Mitheran J, Sanjana Prabhu, Siyuan Chen
In our work, we aim to take a step toward bringing vision transformers to the edge by utilizing popular model compression techniques such as distillation, pruning, and quantization.
1 code implementation • 3 Jul 2023 • Weimin Tan, Siyuan Chen, Bo Yan
Although various few-shot semantic segmentation (FSS) models with different network structures have been proposed, performance improvement has reached a bottleneck.
Ranked #8 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
no code implementations • 23 May 2023 • Siyuan Chen, Mengyue Wu, Kenny Q. Zhu, Kunyao Lan, Zhiling Zhang, Lyuchun Cui
Empowering chatbots in the field of mental health is receiving increasing amount of attention, while there still lacks exploration in developing and evaluating chatbots in psychiatric outpatient scenarios.
2 code implementations • 14 May 2023 • Danyang Zhang, Zhennan Shen, Rui Xie, Situo Zhang, Tianbao Xie, Zihan Zhao, Siyuan Chen, Lu Chen, Hongshen Xu, Ruisheng Cao, Kai Yu
The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks.
no code implementations • 8 Feb 2023 • Siyuan Chen, Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry
Further, batching puts strict restrictions on memory adjacency and can lead to high data movement costs.
no code implementations • 17 Jan 2023 • Yu Gao, Xi Xu, Tianji Jiang, Siyuan Chen, Yi Yang, Yufeng Yue, Mengyin Fu
For example, 2D object detection usually requires a large amount of 2D annotation data with high cost.
no code implementations • 2 Jul 2022 • Yuping Ye, Siyuan Chen, Zhan Song
In this paper, we propose benchmarks that can evaluate the structured light method's performance.
no code implementations • 23 May 2022 • Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Q. Zhu
Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling.
1 code implementation • 19 May 2022 • Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Q. Zhu
Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat.
no code implementations • 16 May 2022 • Junkang Wei, Jin Xiao, Siyuan Chen, Licheng Zong, Xin Gao, Yu Li
The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures challenge users in computational biology for utilizing the structural information and protein surface property representation.
1 code implementation • 26 Jan 2022 • Junfa Lin, Siyuan Chen, Jiahai Wang
GNN-DSR models the short-term dynamic and long-term static interactional representations of the user's interest and the item's attraction, respectively.
no code implementations • 26 Jul 2021 • Junkang Wei, Siyuan Chen, Licheng Zong, Xin Gao, Yu Li
Protein-RNA interactions are of vital importance to a variety of cellular activities.
1 code implementation • 23 Jan 2021 • Siyuan Chen, Jiahai Wang, Guoqing Li
Additionally, the structural prior knowledge, symmetry as a special case, is introduced for better relation prediction in more complex systems.
1 code implementation • 9 Dec 2020 • Zhijian Qiao, Hanjiang Hu, Weiang Shi, Siyuan Chen, Zhe Liu, Hesheng Wang
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance.
no code implementations • SEMEVAL 2020 • Zehao Liu, Emmanuel Osei-Brefo, Siyuan Chen, HuiZhi Liang
In this paper, a Gaussian Mixture Model sampling method is proposed to tackle the problem of class imbalance for the memes sentiment classification task.
1 code implementation • 16 Mar 2020 • Siyuan Chen, Jiahai Wang, Xin Du, Yanqing Hu
The information fusion component adopts a group of encoders and decoders to fuse heterogeneous information and generate discriminative node embeddings for preliminary matching.
no code implementations • 12 Nov 2018 • Oscar Chang, Robert Kwiatkowski, Siyuan Chen, Hod Lipson
Linearly interpolating between the latent embeddings for a good agent and a bad agent yields an agent embedding that generates a network with intermediate performance, where the performance can be tuned according to the coefficient of interpolation.